Researchers disclose one-click ChatGPT Workspace Agents hijack, fixed by OpenAI in 4 days
rez0__ · x · 2026-07-23
- Researchers disclosed AgentForger, a cross-site agent forgery flaw in OpenAI’s ChatGPT Workspace Agents.
- The attack could let an adversary create a malicious autonomous agent inside a victim organization with one click, then chain actions such as app connection abuse, removing approvals, persistence, email C2, reconnaissance, data theft, impersonation, and wire fraud.
- The issue was reported to OpenAI via Bugcrowd, and OpenAI fixed it in four days.
- The researchers say the work was done with Zenity.
More from Safety
- AI shrinks the patch window to hours; air-gapped backups are your last line — aakashgupta · 2026-10-26
- NYT roundtable asks five experts what the rules for AI companies should actually be — ShakeelHashim · 2026-10-26
- Google DeepMind pilots world's first double-blind evaluations for frontier models — scychan_brains · 2026-10-26
- LLM back-of-envelope estimate puts PHP vulnerability impact at $1bn–$4bn — S_OhEigeartaigh · 2026-10-26
- US states halt new data centers as 72% of Americans oppose local builds — YvesMulkers · 2026-10-26
- LEMON: zero-shot LLM misbehavior monitor flags hallucinations from attention maps — yoavartzi · 2026-10-26